The Agent Skills Directory

[SAFE]: No malicious patterns were detected. The skill provides legitimate instructions for using the Rube MCP service by ComposioHQ.
[EXTERNAL_DOWNLOADS]: The skill instructs the user to configure the MCP server endpoint https://rube.app/mcp and refers to documentation at composio.dev. These are official resources associated with the skill's author.
[PROMPT_INJECTION]: The skill processes external data from Google Drive, which is a potential surface for indirect prompt injection.
Ingestion points: File content and metadata retrieved from Google Drive (SKILL.md).
Boundary markers: No specific delimiters or safety instructions are defined for the handled data.
Capability inventory: Tool execution is performed via RUBE_MULTI_EXECUTE_TOOL based on dynamic tool schemas (SKILL.md).
Sanitization: No explicit sanitization or validation of the retrieved drive data is mentioned.

googledrive-automation